Skip to main content
BenchLM
Advertise

Model comparison

DeepSeek V4 Flash (High) vs MiMo-V2-Flash

Data verified

Head-to-head evidence from 18 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

53.95/100
Margin
0.1pts
winning →
54.06/100
0 category wins2 category wins

Public leaderboard positions: DeepSeek V4 Flash (High) #92 (Estimated); MiMo-V2-Flash #91 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. DeepSeek V4 Flash (High) and MiMo-V2-Flash share 18 comparable benchmark results. 2 of 8 categories are comparable. 20 results are unique to DeepSeek V4 Flash (High); 1 to MiMo-V2-Flash.

Updated July 23, 2026
Shared results
18
DeepSeek V4 Flash (High) only
20
MiMo-V2-Flash only
1
Comparable categories
2 / 8

Pick MiMo-V2-Flash if you want the stronger benchmark profile. DeepSeek V4 Flash (High) only becomes the better choice if you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 5 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

MiMo-V2-Flash has the cleaner BenchAlign overall profile here, landing at 54.06 versus 53.95. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

MiMo-V2-Flash's sharpest advantage is in knowledge, where it averages 84.7 against 52.1. The single biggest benchmark swing on the page is SWE-bench Verified, 78.6% to 73.4%.

DeepSeek V4 Flash (High) is also the more expensive model on tokens at $0.14 input / $0.28 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for MiMo-V2-Flash. That is roughly Infinityx on output cost alone. DeepSeek V4 Flash (High) gives you the larger context window at 1M, compared with 256K for MiMo-V2-Flash.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for DeepSeek V4 Flash (High) and MiMo-V2-Flash
CategoryDeepSeek V4 Flash (High)ΔMiMo-V2-Flash
KnowledgeDeepSeek V4 Flash (High)52.1Margin→ 32.6MiMo-V2-Flash84.7
CodingDeepSeek V4 Flash (High)68.5Margin→ 4.9MiMo-V2-Flash73.4
AgenticDeepSeek V4 Flash (High)55.3MarginNo overlapMiMo-V2-FlashNot measured
MathDeepSeek V4 Flash (High)91.9MarginNo overlapMiMo-V2-FlashNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · DeepSeek V4 Flash (High)B · MiMo-V2-Flash

  1. SWE-bench Verified

    Coding
    Source ↗
    A 78.6%B 73.4%
    Winner: DeepSeek V4 Flash (High)Δ 5.2
    SWE-bench Verified: DeepSeek V4 Flash (High) scored 78.6%; MiMo-V2-Flash scored 73.4%. DeepSeek V4 Flash (High) wins this benchmark.

  2. GPQA

    Knowledge
    Source ↗
    A 87.4%B 83.7%
    Winner: DeepSeek V4 Flash (High)Δ 3.7
    GPQA: DeepSeek V4 Flash (High) scored 87.4%; MiMo-V2-Flash scored 83.7%. DeepSeek V4 Flash (High) wins this benchmark.

  3. MMLU-Pro

    Knowledge
    Source ↗
    A 86.4%B 84.9%
    Winner: DeepSeek V4 Flash (High)Δ 1.5
    MMLU-Pro: DeepSeek V4 Flash (High) scored 86.4%; MiMo-V2-Flash scored 84.9%. DeepSeek V4 Flash (High) wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricDeepSeek V4 Flash (High)MiMo-V2-FlashComparison
Input / output priceUSD per 1M tokensDeepSeek V4 Flash (High)$0.14 input / $0.28 outputMiMo-V2-Flash$0 input / $0 outputMiMo-V2-Flash has the lower combined listed price.
Generation speedtokens per secondDeepSeek V4 Flash (High)Not availableMiMo-V2-Flash129 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenDeepSeek V4 Flash (High)Not availableMiMo-V2-Flash2.14 sA complete latency comparison is not available.
Context windowmaximum listed tokensDeepSeek V4 Flash (High)1MMiMo-V2-Flash256KDeepSeek V4 Flash (High) lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkDeepSeek V4 Flash (High)MiMo-V2-FlashResult
Terminal-Bench 2.0Source 56.6%—Not comparable
BrowseCompSource 53.5%—Not comparable
HLE w/ toolsSource 40.3%—Not comparable
MCP AtlasSource 67.4%—Not comparable
ToolathlonSource 43.5%—Not comparable
τ²-bench resultsSource 95.6%83.9%DeepSeek V4 Flash (High) leads
AA Agentic IndexSource 28.2%12.0%DeepSeek V4 Flash (High) leads
GDPval-AASource 32.4%16.7%DeepSeek V4 Flash (High) leads
GDPval-AASource 1147833DeepSeek V4 Flash (High) leads
CodingMiMo-V2-Flash wins
BenchmarkDeepSeek V4 Flash (High)MiMo-V2-FlashResult
CodeforcesSource 2816.0—Not comparable
SWE-bench VerifiedSource 78.6%73.4%DeepSeek V4 Flash (High) leads
SWE-bench ProSource 52.3%—Not comparable
SWE MultilingualSource 70.2%—Not comparable
Terminal-Bench 2.0Source 56.6%—Not comparable
AA-SciCodeSource 42.0%25.9%DeepSeek V4 Flash (High) leads
AA Coding IndexSource 52.0%49.8%DeepSeek V4 Flash (High) leads
Reasoning
BenchmarkDeepSeek V4 Flash (High)MiMo-V2-FlashResult
MRCR 1MSource 76.9%—Not comparable
CorpusQA 1MSource 59.3%—Not comparable
AA-LCRSource 62.7%31.3%DeepSeek V4 Flash (High) leads
CritPtSource 3.4%0.0%DeepSeek V4 Flash (High) leads
KnowledgeMiMo-V2-Flash wins
BenchmarkDeepSeek V4 Flash (High)MiMo-V2-FlashResult
MMLU-ProSource 86.4%84.9%DeepSeek V4 Flash (High) leads
SimpleQASource 28.9%—Not comparable
Chinese-SimpleQASource 73.2%—Not comparable
GPQASource 87.4%83.7%DeepSeek V4 Flash (High) leads
GPQA-DSource 87.4%—Not comparable
HLESource 29.4%—Not comparable
Artificial Analysis Intelligence IndexSource 37.5%24.7%DeepSeek V4 Flash (High) leads
AA-GPQA DiamondSource 86.7%65.6%DeepSeek V4 Flash (High) leads
AA-HLESource 27.8%8.0%DeepSeek V4 Flash (High) leads
AA-Omniscience IndexSource -22.3%-48.5%DeepSeek V4 Flash (High) leads
AA-Omniscience AccuracySource 35.5%15.2%DeepSeek V4 Flash (High) leads
AA-Omniscience Hallucination RateSource 89.7%75.1%MiMo-V2-Flash leads
Math
BenchmarkDeepSeek V4 Flash (High)MiMo-V2-FlashResult
HMMT Feb 2026Source 91.9%—Not comparable
IMOAnswerBenchSource 85.1%—Not comparable
ApexSource 19.1%—Not comparable
Apex ShortlistSource 72.1%—Not comparable
AIME 2025Source —94.1%Not comparable
Multimodal
BenchmarkDeepSeek V4 Flash (High)MiMo-V2-FlashResult
Design Arena WebsiteSource 1238—Not comparable
Inst. Following
BenchmarkDeepSeek V4 Flash (High)MiMo-V2-FlashResult
AA-IFBenchSource 73.5%39.9%DeepSeek V4 Flash (High) leads
Frequently Asked Questions (3)

Which is better, DeepSeek V4 Flash (High) or MiMo-V2-Flash?

MiMo-V2-Flash is ahead on BenchLM's BenchAlign leaderboard, 54.06 to 53.95. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 78.6% and 73.4%.

Which is better for knowledge tasks, DeepSeek V4 Flash (High) or MiMo-V2-Flash?

MiMo-V2-Flash has the edge for knowledge tasks in this comparison, averaging 84.7 versus 52.1. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, DeepSeek V4 Flash (High) or MiMo-V2-Flash?

MiMo-V2-Flash has the edge for coding in this comparison, averaging 73.4 versus 68.5. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

DeepSeek Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.